© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112257
    Prev
    Next
    INDEX
    Explanations

    phrases structured with list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =my
    -0.07
    ela
    -0.07
    ,},↵
    -0.07
     Tourism
    -0.07
     grill
    -0.06
     diner
    -0.06
    esa
    -0.06
     erst
    -0.06
     Abu
    -0.06
     td
    -0.06
    POSITIVE LOGITS
     these
    0.18
    these
    0.17
     THESE
    0.13
    These
    0.12
     These
    0.12
     EVP
    0.11
    them
    0.11
     EVT
    0.10
     investing
    0.10
     them
    0.10
    Activations Density 0.991%

    No Known Activations